Predicting Pedestrian Intention to Cross the Road

Abughalieh, Karam; Alawneh, Shadi

doi:10.1109/access.2020.2987777

Cited by 32 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: The State Of the Artmentioning

confidence: 99%

“…Other different previous works presented in the literature [16], [14], [17], [18] used the SVM model for the intention prediction problem. Some of these works [16], [14], [17] used the output of their pose estimation model in the visual perception extraction. They also focused on different scenarios and used different data sets like the starting, stopping, bending-in and crossing scenarios in Daimler dataset studied by Fang et al [16] and the crossing/N-crossing scenarios in the JAAD dataset used by Fang et al and Abughalieh et al [14], [17].…”

Section: The State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Modular ROS-enabled Pedestrian Intention Prediction Architecture for AVs Maneuvering Control

Manzour,

Elias,

Morgan

et al. 2024

Preprint

View full text Add to dashboard Cite

In this work, the problem of predicting a pedestrian’s intention to cross the road is addressed using visual data captured from a camera. The proposed ROS-based modular architecture consists of four modules starting with the Visual-Perception, Intention Prediction, and the Planning and Control Modules. The visual perception is further divided into three sub-modules. First, pedestrian detection is responsible for detecting the pedestrian and analyzing his state using motion and looking classifiers. Secondly, the detection of the lane that is responsible for analyzing the structured environment which helps in the road state classifiers. The third sub-module aims to extract some curvilinear localization states that are essential for the vehicle’s motion planning and control. The intention prediction module is integrated to capture the pedestrian’s intention to cross the road. In this module, a comparative study is conducted between three different data-driven sequential models. Each model is trained on the JAAD dataset and different extracted features form the visual perception module. It is observed that the proposed GRU model obtained 86% average f1-score, and can predict a pedestrian’s intention three seconds before crossing. In order to control the maneuver of the vehicle, the Proportional-Integral (PI) controller is implemented for longitudinal velocity control to brake the vehicle to avoid collision with the pedestrian, and a Linderoth controller is used to control the lateral motion of the vehicle. Finally, this work is verified on a 1:4 scaled real vehicle to ensure the applicability of implementing this work in real hardware.

show abstract

Section: The State Of the Artmentioning

confidence: 99%

Section: The State Of the Artmentioning

confidence: 99%

Development of a Modular ROS-enabled Pedestrian Intention Prediction Architecture for AVs Maneuvering Control

Manzour,

Elias,

Morgan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Besides the police officer gesture recognition, the actions of other human traffic participants like cyclists [40] or pedestrians [6] are also analyzed in literature. Similar to pedestrian gesture recognition is the pedestrian intention prediction [25,1], where the pedestrian's intention to cross the street should be recognized. Changing the view to the interior of the car, there are approaches to recognize the driver's activities in order to check if the driver is focused on the traffic.…”

Section: Related Workmentioning

confidence: 99%

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

Holzbock,

Kern,

Waldschmidt

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adverse weather conditions, we also demonstrate promising performance when one of the sensors lacks functionality.

show abstract

“…However, CNN are not widely used to predict pedestrian trajectories, because these are non-sequential methods, which makes it difficult to design the network input and output [174]. They are more used for trajectory predictions of road vehicles [208] or the prediction of pedestrian behaviors for autonomous vehicles [209], [210]. The first CNN designed to model and predict pedestrian trajectories is the "Behavior-CNN" from Yi et al [174].…”

Section: B Convolutional Neural Networkmentioning

confidence: 99%

Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches

Korbmacher¹,

Tordeux²

2021

Preprint

View full text Add to dashboard Cite

In crowd scenarios, predicting trajectories of pedestrians is a complex and challenging task depending on many external factors. The topology of the scene and the interactions between the pedestrians are just some of them. Due to advancements in data-science and data collection technologies deep learning methods have recently become a research hotspot in numerous domains. Therefore, it is not surprising that more and more researchers apply these methods to predict trajectories of pedestrians. This paper compares these relatively new deep learning algorithms with classical knowledge-based models that are widely used to simulate pedestrian dynamics. It provides a comprehensive literature review of both approaches, explores technical and application oriented differences, and addresses open questions as well as future development directions. Our investigations point out that the pertinence of knowledge-based models to predict local trajectories is nowadays questionable because of the high accuracy of the deep learning algorithms. Nevertheless, the ability of deep-learning algorithms for large-scale simulation and the description of collective dynamics remains to be demonstrated. Furthermore, the comparison shows that the combination of both approaches (the hybrid approach) seems to be promising to overcome disadvantages like the missing explainability of the deep learning approach.

show abstract

Predicting Pedestrian Intention to Cross the Road

Cited by 32 publications

References 30 publications

Development of a Modular ROS-enabled Pedestrian Intention Prediction Architecture for AVs Maneuvering Control

Development of a Modular ROS-enabled Pedestrian Intention Prediction Architecture for AVs Maneuvering Control

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches

Contact Info

Product

Resources

About